Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    Avoiding or temporary

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     CSS
    -0.06
     trainable
    -0.06
    -card
    -0.06
    R
    -0.06
    iah
    -0.06
    _ROM
    -0.06
     piss
    -0.06
     This
    -0.06
    -ball
    -0.06
    _BUILD
    -0.06
    POSITIVE LOGITS
    なん
    0.06
     canv
    0.06
     поля
    0.06
    Spr
    0.06
     August
    0.06
     المنت
    0.06
     नजर
    0.06
    orge
    0.06
     Girlfriend
    0.06
    (reason
    0.06
    Act Density 0.180%

    No Known Activations